i have done a spearman correlation analysis and all of my independent variables correlated with the dependent variable. However, when i did multiple regression analysis, the results show the iv are not significant. is this possible?
We need more information. Why did you use spearman? What kind of regression did you do? Did you check for collinearity? Did you do a residual plot? All of these things can have a bearing on what you observed. Yes what you observed is possible but let's see if there is another explanation.. Best wishes David Booth
I used spearman because my data is non-normal. i did multiple regression @David Eugene Booth
It is possible, but not likely! You could check this easily by running pairwise Pearson correlations with your variables. If these were all significant and you did not get a significant regression, there is an error somewhere. If you planned to run regression, it didn't make much sense to run Spearman correlations in the first place assuming your ordinal or interval data.
James E. McLean i used spearman cause my data is non-normal. is it okay if I use pearson for nonnormal data? and then, what might cause the error that you mentioned? and is it alright if both of my variables are insignificant even though both correlate with DV? what should I do if I get this result?
Yes it is possible that the four coefficients of your linear regression are not significant even if each of your four variables have a significant correlation with your dependent variable. As David Eugene Booth suggested, collinearity can be the cause. Try omitting the variables one by one. You mentioned non-normal data which is not necessarily a big problem but are you sure that a linear model is appropriate?
Hi Guy Mélard James E. McLean thank you... I've done the collinearity, residual plot, VIFs, Durbin Watson test, and P-Plot, and I understand now. Right now, my result is that only one variable is significant and the other one is not. This should be okay, right?
- Badges
- Science topic